sniklaus/3d-ken-burns

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch

48
/ 100
Emerging

Performs monocular depth estimation to reconstruct 3D geometry, then synthesizes novel camera trajectories with motion parallax effects using differentiable image warping implemented in CuPy CUDA kernels. Includes both an automated pipeline (`autozoom.py`) for one-shot video generation and an interactive web interface for manual camera path adjustment, with output to MP4 via MoviePy.

1,560 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

1,560

Forks

224

Language

Python

License

Last pushed

Jan 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/sniklaus/3d-ken-burns"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.